The Powder Toy

My Tiny Brain 2 by Karakanlud

Karakanlud
Karakanlud
90 / 5
11th Jul 2016
5th Mar 2017
<Updated> This is a prototype for the SFPI challenge. This bot is built with a more complex brain structure; A pseudorandom relaxed signal, a sensory decipherer for wall detectors, excitable motor ganglia and a 2 min memory!
complex malloc complicated complacated basicai sfpi memory neuron brain electronics

Comments

  • the_new_powder99999
    the_new_powder99999     11th Jul 2016
    So, it moves randomly, but if it sees a wall it will move away, and if it remembers that is saw a wall a while ago it moves away. Is there anything I missed?
  • Sylvenia
    Sylvenia     11th Jul 2016
    ok, thanks Karakanlud!
  • Karakanlud
    Karakanlud     11th Jul 2016
    Schmolendevice: ooh I see now. I haven't noticed they were outside of it
  • Karakanlud
    Karakanlud     11th Jul 2016
    Sylvenia: Of course I do! The first two replies were meant for you, I should have tagged you in it.
  • Sylvenia
    Sylvenia     11th Jul 2016
    Hey, Karakanlud, although Schmolendevice did find up a way to make the "logical" decisions with you, the idea/ complaint was mine. Give me at least at little credit!!
  • Schmolendevice
    Schmolendevice     11th Jul 2016
    I see now, the purple auxiliary WIFI at the neuron triplets. Thing is that despite the Gravity Wall, they seem to be "blown away" a few seconds into the simulation.
  • Karakanlud
    Karakanlud     11th Jul 2016
    Proofreading 1 controls reprogramming, proofreading 2 stops the creature 3 pixels before hitting an obstacle, so it won't break.
  • Karakanlud
    Karakanlud     11th Jul 2016
    Memory units act like brick detectors, they reset after a certain amount of time, and the longer duration units provide a less frequent signal. Currently they are connected to GPMPs which guide a powder particle to activate a certain ganglia, and inhibit the opposite one. At ganglias, activation simply sends signal to more synapses from a slowly cooled action potential neuron, so itt will cause longer and more probable signals.
  • Schmolendevice
    Schmolendevice     11th Jul 2016
    Proofreading 1 I guess helps control "decision changes" while Proofreading 2 employs a secondary sensory array for correcting incorrect decisions?
  • Schmolendevice
    Schmolendevice     11th Jul 2016
    I'm presently curious to see how your system "remembers" information. For some reason my debug mode WIFI and Portal "linking lines" are disabled and I cannot easily see which WIFI are connected. For the movement ganglia, I guess that those mini chaos cores simply add to the randomization by causing any queried motor action potential to be of random duration?